{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3FLI5ODOWCBBDIBOYSRYMPXDNY","short_pith_number":"pith:3FLI5ODO","schema_version":"1.0","canonical_sha256":"d9568eb86eb08211a02ec4a3863ee36e0ac0253ad44c2ef4dc5dd4e9925129f6","source":{"kind":"arxiv","id":"2608.12049","version":1},"attestation_state":"computed","paper":{"title":"Token-Level Credit Assignment Optimization for Generative Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daiting Shi, Pengjie Ren, Ran Chen, Xinpeng Zhao, Xin Xin, Xinyu Ma, Yang Liu, Zhaochun Ren, Zhumin Chen","submitted_at":"2026-08-12T13:28:56Z","abstract_excerpt":"Generative retrieval models perform document retrieval by autoregressively generating document identifiers (DocIDs). This process naturally forms a sequential decision problem, where each decoding step selects a DocID token and the complete token sequence determines the retrieved document. However, retrieval effectiveness is typically evaluated only after the full DocID is generated, creating a mismatch between token-level generation and document-level relevance supervision. As a result, existing reinforcement learning methods for generative retrieval mostly rely on sequence-level rewards, whe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.12049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-12T13:28:56Z","cross_cats_sorted":[],"title_canon_sha256":"50950169e250308e08d1c53372e7ffc0adc850513c1e9d42d557a0afdf2131b2","abstract_canon_sha256":"c642236d0c50fe6e0ade595f2322bb5591ce7b579bd9a52bafa3c76030198d40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:29:21.087557Z","signature_b64":"LLiPO6imerG/Lt4AyMlPAINWdWNewfLCFt/HB+mMICcoZT5CNNM7zH0evCTZq2msfK9EfERLKXnmCHOLjsvuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9568eb86eb08211a02ec4a3863ee36e0ac0253ad44c2ef4dc5dd4e9925129f6","last_reissued_at":"2026-08-13T01:29:21.085318Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:29:21.085318Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Token-Level Credit Assignment Optimization for Generative Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daiting Shi, Pengjie Ren, Ran Chen, Xinpeng Zhao, Xin Xin, Xinyu Ma, Yang Liu, Zhaochun Ren, Zhumin Chen","submitted_at":"2026-08-12T13:28:56Z","abstract_excerpt":"Generative retrieval models perform document retrieval by autoregressively generating document identifiers (DocIDs). This process naturally forms a sequential decision problem, where each decoding step selects a DocID token and the complete token sequence determines the retrieved document. However, retrieval effectiveness is typically evaluated only after the full DocID is generated, creating a mismatch between token-level generation and document-level relevance supervision. As a result, existing reinforcement learning methods for generative retrieval mostly rely on sequence-level rewards, whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12049","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.12049/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.12049","created_at":"2026-08-13T01:29:21.086463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12049v1","created_at":"2026-08-13T01:29:21.086463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12049","created_at":"2026-08-13T01:29:21.086463+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FLI5ODOWCBB","created_at":"2026-08-13T01:29:21.086463+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FLI5ODOWCBBDIBO","created_at":"2026-08-13T01:29:21.086463+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FLI5ODO","created_at":"2026-08-13T01:29:21.086463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY","json":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY.json","graph_json":"https://pith.science/api/pith-number/3FLI5ODOWCBBDIBOYSRYMPXDNY/graph.json","events_json":"https://pith.science/api/pith-number/3FLI5ODOWCBBDIBOYSRYMPXDNY/events.json","paper":"https://pith.science/paper/3FLI5ODO"},"agent_actions":{"view_html":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY","download_json":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY.json","view_paper":"https://pith.science/paper/3FLI5ODO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12049&json=true","fetch_graph":"https://pith.science/api/pith-number/3FLI5ODOWCBBDIBOYSRYMPXDNY/graph.json","fetch_events":"https://pith.science/api/pith-number/3FLI5ODOWCBBDIBOYSRYMPXDNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY/action/storage_attestation","attest_author":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY/action/author_attestation","sign_citation":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY/action/citation_signature","submit_replication":"https://pith.science/pith/3FLI5ODOWCBBDIBOYSRYMPXDNY/action/replication_record"}},"created_at":"2026-08-13T01:29:21.086463+00:00","updated_at":"2026-08-13T01:29:21.086463+00:00"}